Object Detection to Identify Shapes of Swallow Nests Using a Deep Learning Algorithm

Indrajaya, Denny; Setiawan, Adi; Hartanto, Djoko; Hariyanto, Hariyanto

doi:10.23917/khif.v8i2.16489

Cited by 5 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the years 2020-2022, the progress of research in the classification of Swiftlet's nest was going on, where object detection was the most studied algorithm to be employed [8]. Some results have been tested for the company through the developed application, which was still a prototype.…”

Section: Deep Learning Classificationmentioning

confidence: 99%

Management of Traditional Business into Modern: from Microsoft Excel to Deep Learning for prototyping classification Swiftlet’s nests

Arini Parhusip,

Trihandaru,

Hartomo

et al. 2024

IJCS

View full text Add to dashboard Cite

In this article, the transformation of traditional management of Swiftlet’s nests into modern business is proposed. Traditional business means that data management of Swiftlet’s nests is done manually, sorted by recording in Microsoft Excel. This is done by PT Waleta Asia Jaya, a company engaged in processing Swiftlet’s nests. This sorting is done because the number of feathers in the Swiftlet’s nests determines the price and cost of workers in processing feather cleaning. In addition, the shape of the Swiftlet’s nests needs attention. However, because it is complex, sorting is done simpler. Originally, Swiftlet’s nests were sorted into 50 categories. To facilitate sorting, deep learning is used with the SSD Mobile Net V2 algorithm as an algorithm to classify into 7 categories based on feather intensity. The device is still a prototype that shows an 85% accuracy rate but has been quite helpful in the process of purchasing Swiftlet’s nests before processing.

show abstract

Section: Deep Learning Classificationmentioning

confidence: 99%

Management of Traditional Business into Modern: from Microsoft Excel to Deep Learning for prototyping classification Swiftlet’s nests

Arini Parhusip,

Trihandaru,

Hartomo

et al. 2024

IJCS

View full text Add to dashboard Cite

show abstract

“…However, this average pooling was not used here. Instead, we employ the global average pooling as shown by (4), which is almost similar to average pooling [11], [15], i.e.,…”

Section: Mobilenetv2-d and Multiple Cameras For Swiftlet Nest Classif...mentioning

confidence: 99%

“…The classification of chili conditions [1], fruit quality classification [2], and classification of unwashed eggs applied to a sorting machine [3] are the examples addressed in the literature. In the case of swiftlet nest detection, swiftlet nests are classified into 3 classes, which apply CNN for feature extraction as well [4]. CNN has been used for various things, including sorting machines.…”

Section: Introductionmentioning

confidence: 99%

MobileNetV2-D and multiple cameras for swiftlet nest classification based on feather intensity

Indrajaya,

Parhusip,

Trihandaru

et al. 2024

IJEECS

View full text Add to dashboard Cite

MobileNetV2-D is a modified version of MobileNetV2, which is the novelty of this article. The algorithm is used to classify swiftlet nests into seven classes. In 2023, PT Waleta Asia Jaya is required to achieve a 7-fold increase in the export quota of swiftlet nests. To meet the quota, the company made a machine that can recognize swiftlet nest objects, which are classified into seven classes based on feather intensity, namely BRS, BR, BST, BS, BBT, BB, and BB2 for the light feathers to the heavy feathers, respectively. The input image is a combination of four images from four cameras with different positions, which adds to the novelty of MobileNetV2-D for the particular problem here. From the evaluation that has been carried out, the accuracy value of the MobileNetV2-D model was better than the MobileNetV2 model, i.e., the accuracy value of the MobileNetV2-D model was 99.9928% for the training dataset and 94.0723% for the testing dataset. Moreover, the speed of MobileNetV2-D is better than MobileNetV2- architecture.

show abstract

“…Nilai confusion matrix dapat dihitung berdasarkan contoh pada Tabel 1, serta dapat digunakan untuk menghitung nilai accuracy, precision dan recall dengan rumus masing-masing pada persamaan (10), (11), dan (12) [24].…”

Section: Evaluasiunclassified

Perbandingan Performa Algoritma Decision Tree untuk Klasifikasi Penerima Beasiswa Bank Indonesia

Dimas Bayu Stiawan,

Nugroho

2023

ijcs

View full text Add to dashboard Cite

Beasiswa dapat diartikan bantuan yang bisa digunakan sebagai biaya penunjang pendidikan, diberikan oleh institusi/lembaga. Pelaksanaan seleksi mahasiswa yang berhak menerima beasiswa didasarkan pada syarat/ketentuan lembaga pemberi beasiswa. Klasifikasi kandidat yang dilakukan dengan Excel menyebabkan sasaran penerima beasiswa kurang tepat karena tidak konsisten disebabkan unsur subjektivitas. Penelitian ini bertujuan menggunakan algoritma Decision Tree ID3, C4.5, serta CART dalam melakukan perbandingan Penerimaan Beasiswa BI untuk melihat algoritma yang memiliki performa terbaik. Penelitian ini menggunakan data sebanyak 398 pendaftar Beasiswa Bank Indonesia tahun 2022 yang diperoleh dari Biro Kemahasiswaan UMS. Hasil evaluasi kinerja ketiga algoritma menunjukkan CART mencapai hasil tertinggi dalam accuracy, precision, dan recall, masing-masing 72%, 92,59%, dan 74,62%. Selanjutnya C4.5 memiliki nilai accuracy, precision, dan recall, masing-masing sebesar 69,33%, 92,30%, dan 71,64%. ID3 memiliki performa terendah, dengan accuracy, precision, dan recall berturutan 68%, 92,15%, dan 70,14%.

show abstract

Object Detection to Identify Shapes of Swallow Nests Using a Deep Learning Algorithm

Cited by 5 publications

References 16 publications

Management of Traditional Business into Modern: from Microsoft Excel to Deep Learning for prototyping classification Swiftlet’s nests

Management of Traditional Business into Modern: from Microsoft Excel to Deep Learning for prototyping classification Swiftlet’s nests

MobileNetV2-D and multiple cameras for swiftlet nest classification based on feather intensity

Perbandingan Performa Algoritma Decision Tree untuk Klasifikasi Penerima Beasiswa Bank Indonesia

Contact Info

Product

Resources

About